Passing Mat to OpenCL kernels causes segmentation error

Question

I want to pass OpenCL Mat to the OpenCL Self-Writing Kernel for FGPA (does not support OpenCV OpenCL).

Host-Code:

Mat img = imread( "template.jpg", IMREAD_GRAYSCALE );
Mat output(img.rows, img.cols, CV_8UC1);
// Program, Context already declared
// Create Kernel
cl_kernel kernel = NULL;
kernel = clCreateKernel(program, "copy", &status);
// Create Command Queue and associate it with the device you want to execute on
cl_command_queue cmdQueue;
cmdQueue = clCreateCommandQueue(context,devices[0], 0,  &status);

// Buffer, prob i do something wrong here
cl_mem buffer_img = clCreateBuffer(context,CL_MEM_READ_ONLY, sizeof(uint) * img.cols * img.rows,    NULL,&status);
cl_mem buffer_outputimg = clCreateBuffer(context,CL_MEM_WRITE_ONLY, sizeof(uint) * img.cols * img.rows,NULL,&status);

status = clEnqueueWriteBuffer(cmdQueue, buffer_img,CL_FALSE,0,sizeof(uint) * img.cols * img.rows,&img,0,NULL,NULL);
// set kernel arguments
status = clSetKernelArg(kernel,0,sizeof(cl_mem),&buffer_img);
status = clSetKernelArg(kernel,1,sizeof(cl_mem),&buffer_outputimg);

size_t globalWorkSize[2];
globalWorkSize[0] = img.cols;
globalWorkSize[1] = img.rows;
status = clEnqueueNDRangeKernel(cmdQueue,kernel,2,NULL, globalWorkSize, NULL,0, NULL,NULL);
clEnqueueReadBuffer(cmdQueue,buffer_outputimg,CL_TRUE,0,sizeof(uint) * img.cols * img.rows, &output,    0,  NULL,   NULL);

//stop cpu till queue is finish
clFinish(cmdQueue);

Kernel code:

__kernel void copy(__global  uchar *  input, __global  uchar *  output) 
{
    const int x = get_global_id(0);
    const int y = get_global_id(1);
    //copy
    output[y * get_global_size(0) + x] = input[y * get_global_size(0) + x] ;
}

When outputting to FPGA, I get a segmentation error, which is probably caused by incorrect processing using Matrix OpenCV.

EDIT : The modified host code proposed by api55 solved the problem:

Mat img = imread( "scene.jpg", IMREAD_GRAYSCALE );
Mat output(img.rows, img.cols, CV_8UC1);
// Program, Context already declared
// Create Kernel
cl_kernel kernel = NULL;
kernel = clCreateKernel(program, "copy", &status);
// Create Command Queue and associate it with the device you want to execute on
cl_command_queue cmdQueue;
cmdQueue = clCreateCommandQueue(context,devices[0], 0,  &status);
checkError(status, "Failed to create commadnqueue");

// Buffer
cl_mem buffer_img = clCreateBuffer(context,CL_MEM_READ_ONLY, sizeof(uchar) * img.cols * img.rows,   NULL,&status);
cl_mem buffer_outputimg = clCreateBuffer(context,CL_MEM_WRITE_ONLY, sizeof(uchar) * img.cols * img.rows,NULL,&status);
checkError(status, "Failed to create buffer_mask");

status = clEnqueueWriteBuffer(cmdQueue, buffer_img,CL_FALSE,0,sizeof(uchar) * img.cols * img.rows,img.data,0,NULL,NULL);
checkError(status, "Failed to enqueue buffer_img");


status = clSetKernelArg(kernel,0,sizeof(cl_mem),&buffer_img);
status = clSetKernelArg(kernel,1,sizeof(cl_mem),&buffer_outputimg);

size_t globalWorkSize[2];
globalWorkSize[0] = img.cols;
globalWorkSize[1] = img.rows;
status = clEnqueueNDRangeKernel(cmdQueue,kernel,2,NULL, globalWorkSize, NULL,0, NULL,NULL);
clEnqueueReadBuffer(cmdQueue,buffer_outputimg,CL_TRUE,0,sizeof(uchar) * img.cols * img.rows, output.data,0,NULL,NULL);

imwrite("output.jpg", output);

Answer 1

I don't have much experience with opencl, but I think this is an opencv / C ++ problem.

The opencv mat data lies in img.data, which is equal to the uchar*size sizeof(T) * channels * rows * cols.

T uchar, 3 ( greyscale img). 3 uchar - 24 , ( ) - 8 , uint, 32 . - . , , , .

&img :

status = clEnqueueWriteBuffer(cmdQueue, buffer_img,CL_FALSE,0,sizeof(uint) * img.cols * img.rows,&img,0,NULL,NULL);

to img.data

, . , opencl uchar, , cv::Mat :

img.convertTo(img, CV_32S);

. int... opencv unsigned int... , (.. sizeof(uint)), , .

float, CV_32F, double CV_64F.